{"id":"https://openalex.org/W2991043234","doi":"https://doi.org/10.1109/hpec.2019.8916494","title":"Multithreaded Layer-wise Training of Sparse Deep Neural Networks using Compressed Sparse Column","display_name":"Multithreaded Layer-wise Training of Sparse Deep Neural Networks using Compressed Sparse Column","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2991043234","doi":"https://doi.org/10.1109/hpec.2019.8916494","mag":"2991043234"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2019.8916494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101457271","display_name":"Mohammad Hasanzadeh Mofrad","orcid":"https://orcid.org/0000-0003-4369-6928"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Hasanzadeh Mofrad","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038997010","display_name":"Rami Melhem","orcid":"https://orcid.org/0000-0001-6403-5446"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rami Melhem","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072934511","display_name":"Yousuf Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Yousuf Ahmad","raw_affiliation_strings":["Carnegie Mellon University in Qatar, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018894377","display_name":"Mohammad Hammoud","orcid":"https://orcid.org/0000-0002-5742-6147"},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohammad Hammoud","raw_affiliation_strings":["Carnegie Mellon University in Qatar, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101457271"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":0.9801,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8270442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"521","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8001719117164612},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7941790819168091},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6452301740646362},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6163938641548157},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6044493317604065},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5627029538154602},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5522409677505493},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5445310473442078},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4582471251487732},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3491278290748596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3096231520175934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001719117164612},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7941790819168091},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6452301740646362},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6163938641548157},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6044493317604065},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5627029538154602},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5522409677505493},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5445310473442078},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4582471251487732},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3491278290748596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3096231520175934},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2019.8916494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W1598993252","https://openalex.org/W2003840611","https://openalex.org/W2007259720","https://openalex.org/W2056999868","https://openalex.org/W2065607954","https://openalex.org/W2089437293","https://openalex.org/W2116341502","https://openalex.org/W2117130368","https://openalex.org/W2123442489","https://openalex.org/W2134237243","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2193413348","https://openalex.org/W2235832317","https://openalex.org/W2300242332","https://openalex.org/W2415655736","https://openalex.org/W2531409750","https://openalex.org/W2727953781","https://openalex.org/W2919115771","https://openalex.org/W2963674932","https://openalex.org/W2973134322","https://openalex.org/W2987484405","https://openalex.org/W3100809954","https://openalex.org/W3100839241","https://openalex.org/W3105937213","https://openalex.org/W3106161546","https://openalex.org/W6687566353","https://openalex.org/W6698200048","https://openalex.org/W6910447991"],"related_works":["https://openalex.org/W3089117407","https://openalex.org/W2115561485","https://openalex.org/W2023373638","https://openalex.org/W1985089255","https://openalex.org/W2153202644","https://openalex.org/W2010970156","https://openalex.org/W2105895556","https://openalex.org/W2733115356","https://openalex.org/W2377593213","https://openalex.org/W4235861380"],"abstract_inverted_index":{"Training":[0],"a":[1,16],"sparse":[2,183],"Deep":[3],"Neural":[4],"Network":[5],"(DNN)":[6],"is":[7,154],"inherently":[8],"less":[9],"memory-intensive":[10],"and":[11,60,75,100,129,138,185,200],"processor-intensive":[12],"compared":[13],"to":[14,29,35,58,83,136,156,163],"training":[15,41,89],"dense":[17,36,42],"(fully-connected)":[18],"DNN.":[19],"In":[20,44],"this":[21,152],"paper,":[22],"we":[23,48,67,79,96,161,177],"utilize":[24],"Sparse":[25,53],"Matrix-Matrix":[26],"Multiplication":[27],"(SpMM)":[28],"train":[30,68],"sparsely-connected":[31],"DNNs":[32],"as":[33],"opposed":[34],"matrix-matrix":[37],"multiplication":[38],"used":[39],"for":[40,88,179],"DNNs.":[43],"our":[45,109,122,124],"C/C++":[46],"implementation,":[47],"extensively":[49],"use":[50,80,162,178],"in-memory":[51],"Compressed":[52],"Column":[54],"(CSC)":[55],"data":[56],"structures":[57],"store":[59],"traverse":[61],"the":[62,69,85,94,98,142,148,157,165,173,186,189,195,198],"neural":[63,70],"network":[64,71],"layers.":[65],"Also,":[66],"layer":[72,78],"by":[73,114,147],"layer,":[74],"within":[76],"each":[77],"1D-Column":[81,158],"partitioning":[82,159],"divide":[84],"computation":[86,166],"required":[87],"among":[90,170],"threads.":[91],"To":[92],"speedup":[93,153],"computation,":[95],"apply":[97],"bias":[99,199],"activation":[101,201],"functions":[102],"while":[103],"executing":[104],"SpMM":[105,168,192],"operations.":[106],"We":[107,150],"tested":[108],"implementation":[110],"using":[111],"benchmarks":[112],"provided":[113,146],"MIT/IEEE/Amazon":[115],"HPEC":[116],"graph":[117],"challenge":[118],"[1].":[119],"Based":[120],"on":[121],"results,":[123],"single":[125],"thread":[126],"(1":[127],"core)":[128],"multithreaded":[130],"(12":[131],"cores)":[132],"implementations":[133],"are":[134],"up":[135],"22\u00d7,":[137],"150\u00d7":[139],"faster":[140],"than":[141],"serial":[143],"Matlab":[144],"results":[145,193],"challenge.":[149],"believe":[151],"due":[155],"that":[160,176],"balance":[164],"of":[167,182,188,191,197],"operations":[169],"computing":[171],"threads,":[172],"efficient":[174],"mechanism":[175],"memory":[180],"(re)allocation":[181],"matrices,":[184],"overlapping":[187],"accumulation":[190],"with":[194],"application":[196],"functions.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}